Device, system, and method for predicting the number of people using facility

Abstract

To provide a device etc. for predicting the number of people using a facility, for predicting the number of scheduled on-site participants and the number of scheduled remote participants with high precision.SOLUTION: A device for predicting the number of people using a facility 10 includes a remote participation rate determining function learning unit 13b that learns a remote participation rate determining function on the basis of information including a result of the number of on-site participants and a schedule result, a schedule information acquiring unit 13c that acquires schedule information including the schedule of a prediction target event, and a scheduled participant number calculation unit 13d that calculates the number of scheduled participants of the prediction target event on the basis of the schedule information, and further includes a scheduled participant number separation unit 13f that calculates the number of scheduled remote participants by multiplying the number of scheduled participants by the remote participation rate, and further calculates the number of scheduled on-site participants by subtracting the number of scheduled remote participants from the number of scheduled participants.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a facility user number prediction device and the like. [Background technology]

[0002] As a system for predicting the number of users of facilities such as office buildings and event venues, for example, the technology described in Patent Document 1 is known. That is, Patent Document 1 describes that "...weighting is performed according to the degree of contribution, which varies for each prediction target time, and a predicted value of the number of people in the area is calculated for each prediction target time." [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6690070 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology described in Patent Document 1 is based on the premise that people participate in events such as conferences on-site, such as employees commuting to a company's office building. Meanwhile, remote participation in a given event from home or elsewhere using the Internet is rapidly spreading. In cases where people can choose between on-site and remote participation, if a computer could predict the number of people participating in each form of participation, this would lead to more efficient operation of on-site facilities, but Patent Document 1 does not describe such technology.

[0005] Therefore, an object of the present disclosure is to provide a facility user number prediction device etc. that predicts the number of planned local participants and the number of planned remote participants with high accuracy. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems, the facility user number prediction device of the present disclosure comprises a remote participation rate determination function learning unit that learns a remote participation rate determination function based on information including the actual number of on-site participants in an event held in the past, the actual number of remote participants in the event, and the planned number of participants that indicates the situation when the event was held; a plan information acquisition unit that acquires plan information including a schedule of an event to be predicted at a specified facility; and a planned number of participants calculation unit that calculates the planned number of participants for the event to be predicted based on the plan information, as well as a planned number of participants separation unit that calculates the planned number of remote participants for the event to be predicted by multiplying the remote participation rate based on the remote participation rate determination function by the planned number of participants, and further calculates the planned number of on-site participants for the event to be predicted by subtracting the planned number of remote participants from the planned number of participants. Effect of the Invention

[0007] According to the present disclosure, it is possible to provide a facility user number prediction device etc. that predicts the number of planned local participants and the number of planned remote participants with high accuracy. [Brief description of the drawings]

[0008] [Figure 1] 1 is a functional block diagram of a facility user number prediction system including a facility user number prediction device according to a first embodiment. FIG. [Diagram 2] 1 is a functional block diagram of a facility user number prediction device according to a first embodiment. FIG. [Diagram 3] 3 is a functional block diagram of a schedule information acquisition unit included in a calculation unit of the facility user number prediction device according to the first embodiment. FIG. [Figure 4] FIG. 2 is an explanatory diagram of an individual schedule acquired by an individual schedule acquisition unit of the facility user number prediction device according to the first embodiment. [Diagram 5] FIG. 2 is an explanatory diagram of a facility schedule acquired by a facility schedule acquisition unit of the facility user number prediction device according to the first embodiment. [Figure 6]FIG. 2 is an explanatory diagram of weather forecast information acquired by a weather forecast acquisition unit of the facility user number prediction device according to the first embodiment. [Figure 7] FIG. 2 is an explanatory diagram of traffic condition information acquired by a traffic condition acquisition unit of the facility user number prediction device according to the first embodiment. [Figure 8] 4 is an explanatory diagram of participant candidate attribute information acquired by a participant attribute acquisition unit of the facility user number prediction device according to the first embodiment; FIG. [Figure 9] 3 is an explanatory diagram of facility attribute information acquired by a facility attribute acquisition unit of the facility user number prediction device according to the first embodiment. FIG. [Figure 10] 4 is a flowchart showing the process of a calculation unit of the facility user number prediction device according to the first embodiment. [Figure 11] 4 is an example of a display screen showing a calculation result of a calculation unit of the facility user number prediction device according to the first embodiment. [Figure 12] FIG. 11 is a functional block diagram of a facility user number prediction device according to a second embodiment. [Figure 13] 13 is a flowchart showing the process of a calculation unit of a facility user number prediction device according to the second embodiment. [Figure 14] FIG. 11 is a functional block diagram of a facility user number prediction device according to a third embodiment. [Figure 15] 13 is a flowchart showing the process of a calculation unit of a facility user number prediction device according to the third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] First Embodiment <Configuration of facility user number prediction system> FIG. 1 is a functional block diagram of a facility user number prediction system 100 including a facility user number prediction device 10 according to the first embodiment. The facility user count prediction system 100 is a system for predicting the number of users of a facility where a specific event will be held. Examples of such events include company work (including meetings and client meetings) and school classes, as well as forums, concerts, seminars, club gatherings, movie screenings, and online game competitions.

[0010] When a person participates in an event, he or she can freely choose between on-site participation and remote participation. Here, "on-site participation" refers to a participation form in which a person travels to the facility where the event is actually held and then participates in the event. "Remote participation" refers to a participation form in which a person connects to a communication device (not shown) of the on-site facility from the terminal device 20 via the network 40, and participates in the event from a location (e.g., home) different from the facility. In "remote participation," a web conferencing tool such as Teams (registered trademark) or Zoom (registered trademark) may be used as appropriate.

[0011] The on-site facility where a particular event takes place may be an indoor facility such as a conference room in an office building, a classroom in a school, a concert hall, or a complex, or it may be an outdoor facility such as an outdoor concert venue or an outdoor stadium.

[0012] As shown in FIG. 1, a facility user number prediction system 100 includes a facility user number prediction device 10, a terminal device 20, a sensor group 30, and a network 40. The facility user number prediction device 10 is a device that predicts the number of users of a facility where a specific event is held. The facility user number prediction device 10 may be configured as a single computer, or may be configured with multiple computers (not shown) connected in a specific manner via a signal line or a network. For example, the function of the facility user number prediction device 10 may be distributed to multiple computers such as a cloud server or an edge server, and these computers may be connected in a specific manner via a network.

[0013] 1, the facility user number prediction device 10 includes a memory unit 11, an input / output unit 12, and a calculation unit 13. Although not shown, the memory unit 11 is configured to include non-volatile memory such as a ROM (Read Only Memory) or a HDD (Hard Disk Drive), and volatile memory such as a RAM (Random Access Memory) or a register. The memory unit 11 stores various programs and information in advance, as well as information acquired from the terminal device 20 and the sensor group 30 via the network 40 and the processing results of the calculation unit 13.

[0014] The input / output unit 12 has a function of acquiring predetermined information from the terminal device 20 and the sensor group 30 via the network 40, and also has a function of outputting the processing result of the calculation unit 13. The calculation unit 13 is, for example, a CPU (Central Processing Unit), which reads out and develops various programs stored in the storage unit 11, and executes predetermined processing. The processing of the calculation unit 13 will be described later.

[0015] The terminal device 20 is a terminal owned by a user. Examples of such terminal devices 20 include personal computers, smartphones, tablets, smart speakers, and smart watches. Although one terminal device 20 is shown in FIG. 1, in reality, each of a large number of users owns a terminal device 20. These users include a service provider (operator) related to a specific event and a service user who may participate in the event.

[0016] 1, the terminal device 20 includes a terminal input unit 21 and a terminal output unit 22. The terminal input unit 21 is, for example, a keyboard or a mouse operated by a user, and accepts information input by the user. The terminal output unit 22 is, for example, a display or a speaker. Note that the terminal output unit 22 may also have a data input function, such as a touch panel display.

[0017] The sensor group 30 collects information on the usage status of local facilities and remote facilities. In the example of FIG. 1, the sensor group 30 includes a camera 30a, a microphone 30b, a human sensor 30c, a door sensor 30d, an entrance / exit management terminal system 30e, and an elevator operation management system 30f. The sensor group 30 further includes a cafeteria payment system 30g, a ToF sensor 30h (Time of Flight Sensor), a LiDAR sensor 30k (Light Detection and Ranging Sensor), a Wi-Fi packet sensor 30m, a Wi-Fi router 30n, and a Web conference report 30p. Note that "Wi-Fi" is a registered trademark.

[0018] The camera 30a captures images of people (local participants) in the on-site facility and is installed at the entrance, exit, ceiling, etc. of the facility. Person recognition processing may be performed based on image data captured by the camera 30a. The microphone 30b detects the voices of the on-site participants and remote participants. The microphone 30b may be installed in, for example, the terminal device 20, or in another predetermined location (for example, the on-site facility).

[0019] The human sensor 30c detects people in the local facility and is installed at the entrance, exit, ceiling, etc. of the facility. The door sensor 30d detects people near the door of the local facility when the door opens and closes automatically. The entrance / exit management terminal system 30e is a system that manages the entrance and exit of each room included in the local facility. The elevator operation management system 30f is a system that manages the operation of the elevator installed in the local facility. In addition, a camera 30a may be installed at the elevator landing or inside the car, and people flow data of the local facility may be generated based on the camera's image capture results and the elevator operation status.

[0020] The cafeteria payment system 30g is a system that manages payments at a cafeteria installed in a local facility. For example, when a person who uses the cafeteria uses a smartphone or card to pay, the time period during which the person used the cafeteria is identified based on the user's identification information. The ToF sensor 30h is a device that irradiates light onto an object and measures the distance to the object based on the time it takes for the reflected light to return. The LiDAR sensor 30k is a device that irradiates a laser beam onto an object and detects the reflected light to measure the distance to the object. These ToF sensor 30h and LiDAR sensor 30k are used to generate people flow data at the local facility.

[0021] The Wi-Fi packet sensor 30m acquires a predetermined probe request issued from the terminal device 20. The Wi-Fi packet sensor 30m may be built into the terminal device 20, or may be installed in a local facility. The Wi-Fi router 30n is a device that relays communication using Wi-Fi. Note that the Wi-Fi packet sensor 30m and the Wi-Fi router 30n may be used to generate people flow data in a local facility. The Web conference report 30p is recorded when a Web conference is held, and is used to grasp the participants of the Web conference and the time of their attendance and departure.

[0022] 1 is an example, and is not limited thereto. Also, it is not necessary to use all of the sensor group 30 shown in FIG. 1, and a part of the sensor group 30 may be used as appropriate. Also, a part of the sensor group 30 may be built into the terminal device 20.

[0023] 1, a facility number of users prediction device 10 is connected to a terminal device 20 via a network 40, and is also connected to a sensor group 30. Predetermined information is transmitted from the terminal device 20 and the sensor group 30 to the facility number of users prediction device 10 via the network 40. In addition, the processing results of the facility number of users prediction device 10 are transmitted to the terminal device 20 of a user (mainly a service provider) via the network 40, and are displayed in a predetermined manner on this terminal device 20.

[0024] <Configuration of the facility user number prediction device> FIG. 2 is a functional block diagram of the facility user number prediction device 10. As described above, the facility user number prediction device 10 includes a memory unit 11, an input / output unit 12, and a calculation unit 13 (see also FIG. 1). The memory unit 11 stores an actual number of local participants 11a, an actual number of remote participants 11b, a planned actual number 11c, a remote participation rate decision function 11d, and facility space information 11e.

[0025] The on-site participant count record 11a is information showing the number of people who participated on-site in a specific event held in the past. That is, the event name, event type, and event schedule (date, start time, end time), as well as the number of people who participated in the event on-site, are associated with the event ID and stored in the storage unit 11 as the on-site participant count record 11a. It should be noted that work at a company is also considered to be included in the "event".

[0026] The remote participant number record 11b is information indicating the number of people who remotely participated in a specific event held in the past. That is, the event name, event type, event date, and the number of people who remotely participated in the event are associated with the event ID and stored in the storage unit 11 as the remote participant number record 11b.

[0027] Note that the actual number of local participants 11a and the actual number of remote participants 11b may be generated based on the information input by the users who participated in the event to the terminal device 20 (see FIG. 1) as well as the detection results of the sensor group 30 (see FIG. 1). If the event organizer knows the number of local participants, the actual number of local participants 11a may be generated based on the information input by the organizer to the terminal device 20 (see FIG. 1) (the same goes for the actual number of remote participants 11b).

[0028] The scheduled results 11c are information indicating the situation when a predetermined event was held in the past. The scheduled results 11c include, for example, the title of the event held in the past, the participation form indicating whether the participants participated in the event locally or remotely, the time period when the event was held, the day of the week when the event was held, the weather on the day when the event was held, and the traffic conditions on the day when the event was held. Examples of the traffic conditions include the traffic congestion on the roads and the crowded trains when the local participants head to the facility for the event. Furthermore, information such as the attributes of the participants of the event (participants' age, sex, occupation, etc.), the travel distance and travel time when the participants participated in the event locally, and the area or maximum capacity of the venue for the event at the facility may be included in the scheduled results 11c. In addition, information such as the location and age of the facility where the event was held may be included in the scheduled results 11c.

[0029] As such planned results 11c, for example, data for the past year or past several years is stored in the storage unit 11. In addition, the planned results 11c may be created based on information input by event participants (service users) or managers (service providers) to the terminal device 20 (see FIG. 1).

[0030] The remote participation rate determination function 11d is a function used when the calculation unit 13 calculates the number of remote participants expected for the event to be predicted. As the remote participation rate determination function 11d, a predetermined regression formula may be used, or a prediction model such as a neural network may be used. The remote participation rate determination function 11d is learned by the remote participation rate determination function learning unit 13b described later.

[0031] The facility space information 11e includes the maximum capacity and site area of ​​the facility where the event is held. In other words, the facility space information 11e is information indicating the size of the event venue. Note that each piece of information stored in the memory unit 11 is updated as appropriate.

[0032] As shown in Fig. 2, the input / output unit 12 includes an input unit 12a and an output unit 12b. The input unit 12a receives information input by a potential participant (service user) or an administrator (service provider) of the event via a terminal device 20 (see Fig. 1) via a network 40 (see Fig. 1). The input unit 12a also receives detection results of the sensor group 30 (see Fig. 1) via the network 40 (see Fig. 1). The above-mentioned "potential participant" refers to a person who may participate in the event.

[0033] The output unit 12b outputs the processing result of the calculation unit 13 in a predetermined manner. For example, the processing result of the calculation unit 13 may be transmitted to the terminal device 20 (see FIG. 1) of the event manager via the output unit 12b and the network 40 (see FIG. 1) in sequence. Also, the processing result of the calculation unit 13 may be displayed in a predetermined manner on the output unit 12b.

[0034] 2, the calculation unit 13 includes a result acquisition unit 13a, a remote participation rate determination function learning unit 13b, a schedule information acquisition unit 13c, a planned number of participants calculation unit 13d, a remote participation rate calculation unit 13e, and a planned number of participants separation unit 13f. The result acquisition unit 13a acquires information indicating past results regarding the event based on information input to the terminal device 20 (see FIG. 1) by potential participants of the event or the organizer, as well as detection results of the sensor group 30 (see FIG. 1). The information acquired by the result acquisition unit 13a is stored in the storage unit 11 as the actual number of local participants 11a, the actual number of remote participants 11b, and the planned number of participants 11c.

[0035] In addition, there may be cases where the same concert has never been held before, such as a one-time concert. In such cases, the calculation unit 13 may generate the actual number of local participants 11a and the actual number of remote participants 11b based on other events with similar event conditions (such as the size of the facilities, the maximum number of people accommodated, the gender, age, and occupation of potential participants, and the average travel distance for local participation).

[0036] The remote participation rate determination function learning unit 13b learns the remote participation rate determination function 11d based on information including the actual number of local participants 11a, the actual number of remote participants 11b, and the planned number of remote participants 11c. As described above, the remote participation rate determination function may be a regression formula or a prediction model such as a neural network. Predetermined table data or map data may be used as the remote participation rate determination function. The remote participation rate determination function 11d learned by the remote participation rate determination function learning unit 13b is stored in the storage unit 11.

[0037] The schedule information acquisition unit 13c acquires schedule information including a schedule of a prediction target event scheduled in a specific facility. Details of the schedule information will be described later. The expected number-of-participants calculation unit 13d calculates the expected number of participants of the event based on the schedule information acquired by the schedule information acquisition unit 13c.

[0038] In addition, in the calculation of the expected number of participants, no distinction is made between local participation and remote participation. In other words, the expected number of participants includes both the number of local participants and the number of remote participants. When the expected number of participants calculation unit 13d calculates the expected number of participants, for example, the number of people who have registered a specific event in their personal schedule may be counted. In addition, the expected number of participants calculation unit 13d may count the number of people who have declared their attendance in an attendance form or a participation application form.

[0039] The remote participation rate calculation unit 13e calculates the remote participation rate for the event by substituting the schedule information acquired by the schedule information acquisition unit 13c into the remote participation rate decision function 11d. Here, the "remote participation rate" is the ratio of the number of people participating remotely to the number of people scheduled to participate in the event.

[0040] The planned number of participants separation unit 13f calculates the planned number of remote participants of the prediction target event by multiplying the planned number of participants by the remote participation rate based on the remote participation rate determination function 11d. Then, the planned number of participants separation unit 13f calculates the planned number of local participants of the prediction target event by subtracting the planned number of remote participants from the planned number of participants. In this way, the planned number of participants separation unit 13f separates the planned number of participants into the planned number of local participants and the planned number of remote participants.

[0041] The calculation result of the expected number of participants separation unit 13f is transmitted to the terminal device 20 (see FIG. 1) of the event manager via the output unit 12b and the network 40 (see FIG. 1). This allows the manager to consider in advance whether the size of the room is appropriate for the number of people expected to participate on-site when holding a future event, and to adjust in advance the number of meals to be provided to participants, the number of cleaning staff for the facilities, etc.

[0042] FIG. 3 is a functional block diagram of the schedule information acquisition unit 13c included in the calculation unit of the facility user number prediction device. As described above, the schedule information acquisition unit 13c acquires schedule information including the schedule of the prediction target event. For example, if the event is a company meeting, the schedule information acquisition unit 13c acquires the schedule information from an in-house schedule management tool or a website via the network 40 (see FIG. 1). In addition, the schedule information acquisition unit 13c may acquire the schedule information based on information input to the terminal device 20 (see FIG. 1) by a potential participant or a manager of the event.

[0043] As shown in FIG. 3, the schedule information acquiring unit 13c includes a personal schedule acquiring unit 131c, a facility schedule acquiring unit 132c, a weather forecast acquiring unit 133c, a traffic condition acquiring unit 134c, a participant attribute acquiring unit 135c, and a facility attribute acquiring unit 136c.

[0044] The personal schedule acquisition unit 131c acquires the personal schedule of each participant candidate during the period during which the prediction target event is held (or the period including before and after the event). As described above, a "participant candidate" is someone who has the possibility of participating in the event. For example, if the event is a company meeting, each employee of the company is a participant candidate. Also, in the case of a concert, people who have purchased tickets to the concert are participant candidates.

[0045] FIG. 4 is an explanatory diagram of an individual schedule D1 acquired by the individual schedule acquiring unit. The personal schedule D1 shown in FIG. 4 is information showing the schedule of each participant candidate. In the example of FIG. 4, a personal ID, a subject, a start date and start time of an event, and an end date and end time of the event are associated with each other. For example, the personal schedule of a participant candidate with a personal ID of "AAA1" shows that there will be a "UUU meeting" from 8:30 to 9:30 on October 1, 2023. The personal schedule D1 may be a schedule as shown in FIG. 4, or may be an attendance form or participation application form showing the participant candidate's intention to participate and the participation form (on-site participation or remote participation).

[0046] The description will be continued by returning to Fig. 3. The facility schedule acquiring unit 132c shown in Fig. 3 acquires a facility schedule for the holding period of the prediction target event (or a period including before and after the holding period).

[0047] FIG. 5 is an explanatory diagram of the facility schedule D2 acquired by the facility schedule acquiring unit. The equipment schedule D2 shown in FIG. 5 is information showing the schedule of the equipment where a specific event will be held. In the example of FIG. 5, the equipment ID, the subject, the start date and start time of the event, and the end date and end time of the event are associated with each other. For example, it is shown that the equipment with the equipment ID "BBB1" will be used for "UUU meeting" from 8:30 to 9:30 on October 1, 2023. The equipment schedule D2 may be a schedule like that of FIG. 5, or may be information in which the availability of the equipment is associated with the date and time period.

[0048] The weather forecast acquisition unit 133c shown in FIG. 3 acquires weather forecast information for the holding period of the prediction target event (or the period including before and after the holding period).

[0049] FIG. 6 is an explanatory diagram of the weather forecast information D3 acquired by the weather forecast acquisition unit. In the example of weather forecast information D3 shown in Fig. 6, a region ID, a prediction target date, a prediction target time, weather, and a weekday / weekend are associated with each other. For example, in a region with a region ID of "CCC1", the weather is shown to be cloudy from 00:30 to 1:00 on October 1, 2023 (weekend). It should be noted that in addition to Saturdays and Sundays, holidays and public holidays are also included in "weekend".

[0050] 3 acquires traffic condition information for the period during which the prediction target event is held (or the period including before and after the event period). Examples of such traffic condition information include train operation prediction information and road congestion prediction information.

[0051] FIG. 7 is an explanatory diagram of the traffic condition information D4 acquired by the traffic condition acquisition unit. FIG. 7 shows a case where the traffic condition information D4 is train operation prediction information. In the example of the traffic condition information D4 shown in FIG. 7, a line ID, a direction when the train runs (upward or downward), a prediction target date, a prediction target time, a train status, and a section where the train runs are associated with each other. For example, on a line with a line ID of "DDD1", an up train in section EEE1 departing at 4:30 on October 1, 2023 is predicted (scheduled) to run as usual. This train is a train that a potential participant is likely to ride when moving from his / her home or the like to the facility of the event. For example, it is estimated that the potential participant (local participant) will ride the train described above based on the home address of the potential participant, the address of the facility where the event is held, as well as the personal schedule of the potential participant and the date of the event.

[0052] 3 acquires participant candidate attribute information indicating attributes of each participant candidate of the event to be predicted. Examples of the attributes of such participant candidates include the age, sex, and occupation of the participant candidates, as well as the place of residence (address) and family structure.

[0053] FIG. 8 is an explanatory diagram of the participant candidate attribute information D5 acquired by the participant attribute acquisition unit. 8, the personal ID, age, sex, residence ID, family structure, and occupation of the event participant candidate are associated with each other. For example, a participant candidate with a personal ID of "FFF1" is a 37-year-old woman with a residence ID of "GGG1" and is a "housewife" who is "married with no children."

[0054] The facility attribute acquisition unit 136c shown in FIG. 3 acquires facility attribute information indicating the attributes of the facility of the event to be predicted.

[0055] FIG. 9 is an explanatory diagram of facility attribute information D6 acquired by the facility attribute acquisition unit. In the example of facility attribute information D6 shown in Fig. 9, a facility ID, a location ID, the capacity of the facility, and the age of the facility are associated with each other. For example, a facility with a facility ID of "LLL1" has a location ID of "MMM1", a capacity of 1000 people, and is 5 years old. Information indicating the size of the facility in the facility attribute information D6 ("Capacity" in the example of Fig. 9) is used as facility space information 11e (see Fig. 2).

[0056] The "schedule information" acquired by the schedule information acquisition unit 13c (see FIG. 3) includes, for example, a personal schedule D1 (see FIG. 4), a facility schedule D2 (see FIG. 5), weather forecast information D3 (see FIG. 6), traffic condition information D4 (see FIG. 7), participant candidate attribute information D5 (see FIG. 8), and facility attribute information D6 (see FIG. 9). Note that some of these types of information may be used as the "schedule information", and other predetermined information may be added to the "schedule information".

[0057] <Processing by the facility user number prediction device> FIG. 10 is a flowchart showing the processing of the calculation unit of the facility user number prediction device (also see FIG. 2 as appropriate). In step S101, the calculation unit 13 of the facility user number prediction device 10 learns the remote participation rate decision function 11d by the remote participation rate decision function learning unit 13b. That is, the calculation unit 13 learns the remote participation rate decision function 11d based on information including the on-site participant number record 11a, the remote participant number record 11b, and the scheduled record 11c (remote participation rate decision function learning step). The remote participation rate decision function 11d learned in this way is stored in the storage unit 11.

[0058] Next, in step S102, the calculation unit 13 acquires schedule information related to the prediction target event by the schedule information acquisition unit 13c (schedule information acquisition step). That is, the calculation unit 13 acquires information such as personal schedules D1 (see FIG. 4) of the participant candidates, facility schedules D2 (see FIG. 5) related to the event, weather forecast information D3 (see FIG. 6), traffic condition information D4 (see FIG. 7), participant candidate attribute information D5 (see FIG. 8), and facility attribute information D6 (see FIG. 9).

[0059] In step S103, the calculation unit 13 calculates the number of expected participants of the prediction target event by the expected number of participants calculation unit 13d (expected number of participants calculation step). For example, the calculation unit 13 calculates the number of expected participants of the event by counting the number of people who have registered a specific event in their personal schedule. As described above, in the calculation of the expected number of participants, no particular distinction is made between local participation and remote participation.

[0060] In step S104, the calculation unit 13 calculates a remote participation rate by the remote participation rate calculation unit 13e. That is, the calculation unit 13 calculates a remote participation rate in the event to be predicted by substituting the schedule information acquired in step S102 into a remote participation rate determination function (for example, a neural network).

[0061] In step S105, the calculation unit 13 separates the planned number of participants into the planned number of local participants and the planned number of remote participants by the planned number of participants separation unit 13f (planned number of participants separation step). First, the facility user number prediction device 10 calculates the planned number of remote participants by multiplying the planned number of participants by the remote participation rate. Then, the facility user number prediction device 10 calculates the planned number of local participants by subtracting the planned number of remote participants from the planned number of participants.

[0062] In step S106, the calculation unit 13 displays the calculation result via the output unit 12b. For example, the calculation unit 13 transmits information on the calculation result to the terminal device 20 (see FIG. 1) of the event planner or manager via the output unit 12b and the network 40 (see FIG. 1) in sequence. As a result, the terminal device 20 displays the values ​​of the number of people expected to participate on-site and the number of people expected to participate remotely.

[0063] In step S107, the calculation unit 13 adjusts and selects the facilities and services to be provided. For example, if multiple candidate facilities are presented by the event planner or the facility manager, the calculation unit 13 may select a facility with a size appropriate for the number of people expected to participate on-site, and display it on the terminal device 20 of the event planner, etc. Also, the decision corresponding to step S107 may be made by the event planner or the facility manager.

[0064] In addition, the event planner may consider the number of meals to be provided to on-site participants, the number of cleaning staff to clean the facilities, and the selection of a web conferencing system, etc. This can reduce the operation costs of the event by preventing the event from being held in facilities that are unnecessarily large for the number of on-site participants, or by preventing the number of meals or cleaning staff from being too large.

[0065] FIG. 11 is an example of a display screen showing the calculation results of the calculation unit of the facility user number prediction device. In the example of FIG. 11, the equipment ID of the equipment where the event is held, the date and time of the event, the number of people scheduled to participate on-site, the number of people scheduled to participate remotely, and the remote participation rate are displayed in association with each other. For example, in the equipment with the equipment ID "BBB1", for the "UUU meeting" starting at 8:30 on October 1, 2023, it is displayed that the number of people scheduled to participate on-site is 5, the number of people scheduled to participate remotely is 3, and the remote participation rate is 38%. In this way, it is preferable that the output unit 12b displays the number of people scheduled to participate on-site and the number of people scheduled to participate remotely on the user's terminal device 20 (see FIG. 1) in association with the remote participation rate. This allows the event planner, etc. to grasp at a glance the number of people scheduled to participate on-site and the number of people scheduled to participate remotely in a given event.

[0066] <Effects> According to the first embodiment, the calculation unit 13 can predict the number of people expected to participate on-site and the number of people expected to participate remotely with high accuracy based on the learning result of the remote participation rate determination function. This allows the planner to appropriately select the facility where the event will be held, and also prevents waste in the number of meals provided on-site and the number of cleaning staff. As a result, the operation costs of the event can be reduced more than ever before. In addition, it is also possible to select the content of advertisements to be posted in on-site facilities based on the gender and age of people expected to participate on-site.

[0067] Second Embodiment The second embodiment differs from the first embodiment in that information on the specific facility utilization rate 11f (see FIG. 12) is stored in the memory unit 11A (see FIG. 12) of the facility user number prediction device 10A (see FIG. 12) and that the calculation unit 13A (see FIG. 12) includes a specific facility planned number of users calculation unit 13g (see FIG. 12). Note that the other points are the same as those of the first embodiment. Therefore, only the parts that are different from the first embodiment will be described, and the explanation of the overlapping parts will be omitted.

[0068] FIG. 12 is a functional block diagram of a facility user number prediction device 10A according to the second embodiment. As shown in Fig. 12, the facility user number prediction device 10A includes a storage unit 11A, an input / output unit 12, and a calculation unit 13A. In addition to the components described in the first embodiment (see Fig. 2), the storage unit 11A also stores a specific facility utilization rate 11f. The specific facility utilization rate 11f is the ratio of the number of users of a specific facility to the number of on-site participants. Furthermore, a "specific facility" is a facility for a specific purpose that is included in the facility where the event is held. Examples of such "specific facilities" include restaurants and cafes, as well as playgrounds, entertainment facilities, nursing rooms, and toilets.

[0069] The specific equipment utilization rate 11f is set in advance based on statistical information already obtained about the use of the specific equipment. For example, when the specific equipment is a company cafeteria, the average value of the ratio of the number of past cafeteria users to the number of past attendances included in the on-site attendance record 11a is used as the value of the specific equipment utilization rate 11f. The number of past attendances is obtained, for example, from the entrance / exit management terminal system 30e (see FIG. 1). The number of past cafeteria users is obtained, for example, from the cafeteria payment system 30g (see FIG. 1).

[0070] The calculation unit 13A includes a specific equipment user number calculation unit 13g in addition to the components described in the first embodiment (see FIG. 2). The specific equipment user number calculation unit 13g multiplies the number of people expected to attend on-site by the specific equipment usage rate 11f to calculate the number of people expected to use the specific equipment in the event to be predicted. Here, the "number of people expected to use the specific equipment" is the number of people expected to use the specific equipment on the day of the event.

[0071] FIG. 13 is a flowchart showing the processing of the calculation unit of the facility user number prediction device (also see FIG. 12 as appropriate). 13 is the same as that in the first embodiment (see FIG. 10), and therefore the description thereof will be omitted. After the planned number of participants is separated into the planned number of local participants and the planned number of remote participants in step S105, the processing of the calculation unit 13A proceeds to step S116.

[0072] In step S116, the calculation unit 13A calculates the number of people expected to use the specific equipment by the specific equipment user number calculation unit 13g. That is, the calculation unit 13A calculates the number of people expected to use the specific equipment by multiplying the number of people expected to participate on-site calculated in step S105 by the specific equipment utilization rate.

[0073] In step S117, the calculation unit 13A displays the calculation result. That is, the calculation unit 13A displays the number of people expected to participate on-site, the number of people expected to participate remotely, and the remote participation rate on the terminal device 20 (see FIG. 1) of the event planner or the facility manager, as well as the number of people expected to use the specific facility. This allows the event planner or the like to know in advance how many people will use the specific facility on the day of the event.

[0074] In step S118, the calculation unit 13A adjusts and selects the services to be provided in the specific equipment. For example, the calculation unit 13A selects and adjusts the number of meals and the types of menu to be prepared in the cafeteria (specific equipment). Note that AI (Artificial Intelligence) may be used as appropriate in the processing of step S118. Also, the decision corresponding to the processing of step S118 may be made by the operator of the cafeteria.

[0075] <Effects> According to the second embodiment, the event planner or the like can grasp the predicted number of users of specific equipment such as a cafeteria. Therefore, it is possible to prevent the number of meals from being over or under served, thereby reducing the operating costs of the specific equipment.

[0076] Third Embodiment The third embodiment differs from the first embodiment in that a calculation unit 13B (see FIG. 14) of a facility user number prediction device 10B (see FIG. 14) includes a space utilization rate calculation unit 13h (see FIG. 14). The other points are the same as those of the first embodiment. Therefore, only the parts that are different from the first embodiment will be described, and the description of the overlapping parts will be omitted.

[0077] FIG. 14 is a functional block diagram of a facility user number prediction device 10B according to the third embodiment. As shown in Fig. 14, facility user number prediction device 10B includes a storage unit 11, an input / output unit 12, and a calculation unit 13B. In addition to the components described in the first embodiment (see Fig. 2), calculation unit 13B includes a space utilization rate calculation unit 13h. Space utilization rate calculation unit 13h calculates the space utilization rate of the event venue by dividing the number of people expected to participate on-site by the area (or maximum capacity) of the event venue in the facility. Here, "space utilization rate" is a value that indicates the degree of crowding of people in the event venue.

[0078] FIG. 15 is a flowchart showing the process of the facility user number prediction device (also refer to FIG. 14 as necessary). 15 are the same as those in the first embodiment (see FIG. 10), and therefore will not be described. After the planned number of participants is separated into the planned number of local participants and the planned number of remote participants in step S105, the process of the calculation unit 13B proceeds to step S126.

[0079] In step S126, the calculation unit 13B calculates the space utilization rate of the facility where the event is held by the space utilization rate calculation unit 13h. That is, the calculation unit 13B calculates the space utilization rate by dividing the number of people expected to participate on-site by the area (or maximum capacity) of the event venue.

[0080] In step S127, the calculation unit 13B displays the calculation result. That is, the calculation unit 13B displays the number of people expected to participate on-site, the number of people expected to participate remotely, and the remote participation rate on the terminal device 20 (see FIG. 1) of the event planner or the facility manager, as well as the space utilization rate of the facility. This allows the degree of crowding of people expected to participate on-site at the event venue to be known in advance.

[0081] In step S128, the calculation unit 13B evaluates the energy consumption and the demand peak. For example, the calculation unit 13B inputs the value of the space utilization rate into a predetermined energy simulation tool. This calculates the energy consumption and the demand peak in each time period of the equipment where the event is held. The breakdown of the energy consumption of the equipment is, for example, the power consumption of equipment such as air conditioners, lighting equipment, and computers. In the energy simulation tool, the power consumption of the air conditioners in each time period is calculated based on information including the volume of the event venue, the space utilization rate, the average heat generation per person, the weather and outside temperature in the time period when the event is held, the specifications of the air conditioners, and the insulation of the walls of the equipment. In other words, the power consumption of the equipment at every moment is calculated based on information including the space utilization rate, and further the power consumption in each time period is calculated. In addition, the power consumption of the lighting equipment and the computer is also calculated appropriately.

[0082] If the momentary power consumption of the facility based on the information including the space utilization rate is predicted to exceed a predetermined contracted power, the output unit 12b may display a screen on the user's terminal device 20 (see FIG. 1) proposing a change in the venue or schedule of the predicted event so that the power consumption falls below the contracted power. This can reduce the facility's power costs.

[0083] In addition, when the space utilization rate of the facility is equal to or higher than a first predetermined value, the output unit 12b may display a screen on the user's terminal device 20 (see FIG. 1) proposing a change in the venue or schedule of the event to be predicted so as to lower the space utilization rate. The first predetermined value is a threshold value of the space utilization rate that is a criterion for determining whether or not to propose a change in the venue or schedule of the event to be predicted, and is set in advance. This can support the decision-making of event planners and the like, and can also prevent on-site participants from contracting infectious diseases such as the new coronavirus.

[0084] In addition, when the space utilization rate of the facility is equal to or lower than a second predetermined value, the output unit 12b may display a screen on the user's terminal device 20 (see FIG. 1) proposing a change in the venue or schedule of the event to be predicted so as to increase the space utilization rate. The second predetermined value is a threshold value of the space utilization rate that is a criterion for determining whether or not to propose a change in the venue or schedule of the event to be predicted, and is set in advance as a value lower than the first predetermined value. This makes it possible to prevent an event from being held in a facility that is unnecessarily large for the number of on-site participants, thereby reducing the operation costs of the event.

[0085] Note that AI (Artificial Intelligence) may be appropriately used in the process of step S128. Also, the decision corresponding to the process of step S128 may be made by the planner of the event, etc.

[0086] <Effects> According to the third embodiment, the space utilization rate of an event venue can be predicted with high accuracy, and the prediction result can be displayed on the terminal device 20 of the event planner, etc. Also, the event planner, etc. can change the equipment or change the schedule of the event so that the moment-to-moment power consumption of the equipment based on the space utilization rate does not exceed a predetermined contract power.

[0087] <<Variations>> The facility user number prediction system 100 and the facility user number prediction device 10 according to the present disclosure have been described above in each embodiment, but they are not limited to these descriptions and various modifications can be made. For example, in the embodiment, a case where each of the participant candidates can freely select either on-site participation or remote participation has been described, but this is not limited to this. That is, each embodiment can also be applied to a case where the participation form (on-site participation or remote participation) is predetermined for some of the participant candidates, and the remaining participant candidates can freely select either on-site participation or remote participation.

[0088] In addition, in each embodiment, the case where the planned number of remote participants is calculated based on the remote participation rate has been described, but this is not limited to this. That is, the calculation unit 13 may calculate the local participation rate and multiply the planned number of participants by the local participation rate to calculate the planned number of local participants.

[0089] In each embodiment, the case where the result acquisition unit 13a (see FIG. 2) acquires the actual number of local participants 11a (see FIG. 2), the actual number of remote participants 11b (see FIG. 2), and the scheduled result 11c (see FIG. 2) has been described, but this is not limited to the above. For example, past schedule information acquired by the schedule information acquisition unit 13c (see FIG. 2) may be used as the scheduled result 11c.

[0090] The present disclosure is not limited to the above-described embodiments, but includes various modified examples. For example, each embodiment has been described in detail to clearly explain the present disclosure, and is not necessarily limited to those having all of the configurations described. In addition, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another example to the configuration of one embodiment. In addition, it is possible to add, delete, or replace a part of the configuration of each embodiment with another configuration.

[0091] In addition, the above-mentioned configurations, functions, processing units, processing means, etc. may be realized in part or in whole by hardware, for example, by designing them as integrated circuits. In addition, the above-mentioned configurations, functions, etc. may be realized in software by a processor interpreting and executing a program that realizes each function. Information such as the program, table, file, etc. that realizes each function can be stored in a memory, a recording device such as a hard disk or SSD (Solid State Drive), or a recording medium such as an IC card, SD card, or DVD. In addition, the control lines and information lines shown are those that are considered necessary for the explanation, and not all control lines and information lines in the product are necessarily shown. In reality, it can be considered that almost all components are connected to each other. [Explanation of symbols]

[0092] 10, 10A, 10B Facility user number prediction device 11,11A Storage section 11a Number of local participants 11b Number of remote participants 11c Planned Results 11d Remote participation rate decision function 11e Equipment space information 11f Specific equipment utilization rate 12 Input / output section 12a Input section 12b Output section 13,13A,13B calculation section 13a Performance Acquisition Section 13b Remote participation rate decision function learning part 13c Schedule information acquisition section 13d Participant Count Calculation Section 13e Remote Participation Rate Calculation Department 13F Participant separation section 13g Calculation of the number of people expected to use specific equipment 13h Space occupancy rate calculation section 20 Terminal Equipment 30 Sensors 40 Network 100 Facility User Prediction System

Claims

1. a remote participation rate determination function learning unit that learns a remote participation rate determination function based on information including a record of the number of local participants in a past event, a record of the number of remote participants in the event, and a record of the planned number of participants in the event, the planned number of participants in the event, and the planned number of participants in the event; a schedule information acquisition unit that acquires schedule information including a schedule of a prediction target event scheduled in a predetermined facility; a planned number of participants calculation unit that calculates a planned number of participants for the prediction target event based on the schedule information; a planned number of participants separation unit that calculates the number of planned remote participants for the predicted event by multiplying the planned number of participants by a remote participation rate based on the remote participation rate determination function, and further calculates the number of planned on-site participants for the predicted event by subtracting the planned number of remote participants from the planned number of participants.

2. The planned results include the title of the event held in the past, the participation form indicating whether the participants participated in the event on-site or remotely, the time period during which the event took place, the day of the week on which the event took place, the weather on the day on which the event took place, the traffic conditions on the day on which the event took place, the attributes of the participants of the event, the distance traveled when the participants participated in the event on-site, and the area or maximum capacity of the venue for the event at the facility.

2. The facility user number prediction device according to claim 1,

3. An output unit is provided that displays the number of people expected to participate on-site and the number of people expected to participate remotely on a user's terminal device in association with a remote participation rate.

2. The facility user number prediction device according to claim 1,

4. A specific equipment utilization rate is set, which is the ratio of the number of users of specific equipment included in the equipment to the number of local participants; a specific equipment usage planned number calculation unit that calculates the number of people who are expected to use the specific equipment in the event to be predicted by multiplying the number of people who are expected to participate on-site by the specific equipment usage rate; 2. The facility user number prediction device according to claim 1,

5. A space utilization rate calculation unit is provided that calculates a space utilization rate of the event venue by dividing the number of people expected to participate on-site by the area or maximum capacity of the event venue in the facility.

2. The facility user number prediction device according to claim 1,

6. and an output unit that displays, when the space utilization rate is equal to or higher than a first predetermined value, a screen proposing to change the venue or schedule of the event to be predicted so as to reduce the space utilization rate on a user's terminal device.

6. The facility user number prediction device according to claim 5,

7. and an output unit that, when the space utilization rate is equal to or lower than a second predetermined value, displays on a user's terminal device a screen that suggests changing the venue or schedule of the event to be predicted so as to increase the space utilization rate.

6. The facility user number prediction device according to claim 5,

8. and an output unit that, when it is predicted that the momentary power consumption of the facility based on information including the space utilization rate will exceed a predetermined contract power, displays on a user's terminal device a screen proposing a change in the venue or schedule of the predicted event so that the power consumption falls below the contract power.

6. The facility user number prediction device according to claim 5,

9. a remote participation rate determination function learning unit that learns a remote participation rate determination function based on information including a record of the number of local participants in a past event, a record of the number of remote participants in the event, and a record of the planned number of participants in the event, the planned number of participants in the event, and the planned number of participants in the event; a schedule information acquisition unit that acquires schedule information including a schedule of a prediction target event scheduled in a predetermined facility; a planned number of participants calculation unit that calculates a planned number of participants for the prediction target event based on the schedule information; a planned number of participants separation unit that calculates the number of planned remote participants for the predicted event by multiplying the planned number of participants by a remote participation rate based on the remote participation rate determination function, and further calculates the number of planned on-site participants for the predicted event by subtracting the planned number of remote participants from the planned number of participants.

10. A remote participation rate determination function learning step in which a calculation unit learns a remote participation rate determination function based on information including a record of the number of local participants in a past event, a record of the number of remote participants in the event, and a record of the planned number of participants in the event, the planned number of participants being the same, and the situation when the event was held; A schedule information acquisition step in which the calculation unit acquires schedule information including a schedule of a prediction target event scheduled in a predetermined facility; and a planned number of participants calculation step in which the calculation unit calculates a planned number of participants for the prediction target event based on the schedule information, the calculation unit calculates the number of planned remote participants for the event to be predicted by multiplying the remote participation rate based on the remote participation rate determination function by the planned number of participants, and further calculates the number of planned on-site participants for the event to be predicted by subtracting the planned number of remote participants from the planned number of participants.

Images